后台店铺数据记录页新增 Tab 切换与重复 ASIN 分析；task-169/170 HTTP 客户端配置接入；dedupe/brand 相关改造

- 管理后台：店铺数据记录改为列表分页展示（去任务号/文件列/累计标题，'最新'改'更新时间'），新增'重复 ASIN' Tab 按跨店聚合展示 ASIN/店铺/分组/国家/日期/价格；修复失败/进行中任务被过滤不显示的问题
- task-169: BrandCheckHttpConfigResolver 从 aiimage.http-client.* 读取品牌检查超时/重试（默认同现状、钳制），附 8 条测试
- task-170: surefire 内存调整为 1536m
- dedupe: DedupeRunService 重构（事务边界/进度）、新增 DedupeRunProgressVo、Controller 与结果 VO 调整，PermissionMenuService 相应适配
- brand/dedupe 前端：BrandDedupeTab/BrandPatrolDeleteTab 改造、新增 CountrySelector 组件与 country-options、类型与接口端对齐、测试更新
- 移除无引用文件：backend/static/logo.jpg、prompts/

backend/blueprints/admin_api.py

@@ -1,6 +1,7 @@
 """
 管理员 API 蓝图：用户管理、生成历史、版本管理（后台）
 """
+import io
 import json
 import os
 import re
@@ -13,6 +14,8 @@ from pathlib import Path
 from urllib.parse import quote
 
 import requests
+from openpyxl import load_workbook
+from openpyxl.utils.exceptions import InvalidFileException
 from requests.adapters import HTTPAdapter
 from flask import (
     Blueprint,
@@ -1690,6 +1693,268 @@ def _load_shop_data_crawl_download_rows(result_ids):
         conn.close()
 
 
+_SHOP_DATA_CRAWL_ASIN_ANALYSIS_MAX_BYTES = 256 * 1024 * 1024
+_SHOP_DATA_CRAWL_ASIN_ANALYSIS_TIMEOUT = (10, 60)
+
+
+def _shop_data_crawl_fetch_result_bytes(row, timeout=None):
+    """从 Java 下载接口拉取结果文件字节流（仅内存，不落盘）。"""
+    url = f"{backend_java_base_url}/api/admin/shop-data-crawl/results/{int(row['id'])}/download"
+    headers, params = _backend_java_internal_request()
+    response = _get_backend_java_session().get(
+        url,
+        params=params,
+        headers=headers,
+        stream=True,
+        timeout=timeout or _SHOP_DATA_CRAWL_ASIN_ANALYSIS_TIMEOUT,
+    )
+    try:
+        response.raise_for_status()
+        total = 0
+        chunks = []
+        for chunk in response.iter_content(chunk_size=1024 * 1024):
+            if not chunk:
+                continue
+            total += len(chunk)
+            if total > _SHOP_DATA_CRAWL_ASIN_ANALYSIS_MAX_BYTES:
+                raise ValueError('结果文件过大，无法分析')
+            chunks.append(chunk)
+        return b''.join(chunks)
+    finally:
+        response.close()
+
+
+def _shop_data_crawl_cell_text(cell):
+    """读取单元格文本：日期/数字等统一转字符串，None 返回空串。"""
+    if cell is None:
+        return ''
+    value = cell.value
+    if value is None:
+        return ''
+    if isinstance(value, datetime):
+        return value.strftime('%Y-%m-%d')
+    if isinstance(value, float) and value.is_integer():
+        return str(int(value))
+    return str(value).strip()
+
+
+def _shop_data_crawl_parse_workbook(workbook):
+    """从结果 Workbook 提取 ASIN 行：字典列表，表头按 日期/ASIN/…/价格/…/品牌 识别，跳过无 ASIN 行。"""
+    rows = []
+    for sheet in workbook.worksheets:
+        header_cells = list(next(sheet.iter_rows(min_row=1, max_row=1), []))
+        header = [_shop_data_crawl_cell_text(cell) for cell in header_cells]
+        try:
+            asin_col = header.index('ASIN')
+        except ValueError:
+            continue
+        date_col = header.index('日期') if '日期' in header else None
+        price_col = header.index('价格') if '价格' in header else None
+        brand_col = header.index('品牌') if '品牌' in header else None
+        for sheet_row in sheet.iter_rows(min_row=2):
+            asin = _shop_data_crawl_cell_text(sheet_row[asin_col])
+            if not asin:
+                continue
+            rows.append({
+                'asin': asin,
+                'date': _shop_data_crawl_cell_text(sheet_row[date_col]) if date_col is not None else '',
+                'price': _shop_data_crawl_cell_text(sheet_row[price_col]) if price_col is not None else '',
+                'brand': _shop_data_crawl_cell_text(sheet_row[brand_col]) if brand_col is not None else '',
+            })
+    return rows
+
+
+@admin_api.route('/shop-data-crawl/duplicate-asins')
+@login_required
+def shop_data_crawl_duplicate_asins():
+    """按当前店铺列表筛选条件，分析跨店铺重复的 ASIN 明细。
+
+    读取当前页每家店铺最新结果 Excel（经 Java 下载接口拉取），按 ASIN 聚合
+    其出现的店铺、国家与「日期/价格/品牌」细节，仅返回出现在 2 家及以上店铺
+    的 ASIN（按店铺数降序、ASIN 升序），空 pagination 参数时返回全量用于导出。
+    """
+    _, _, denied = _ensure_backend_menu_access('shop-data-crawl-tasks')
+    if not denied:
+        _, _, denied = _ensure_shop_data_crawl_data_access()
+    if denied:
+        return denied
+    try:
+        page = max(1, int(request.args.get('page', 1)))
+        page_size = min(100, max(10, int(request.args.get('page_size', 20))))
+        shop_name = (request.args.get('shop_name') or request.args.get('shop') or '').strip()
+        group_name = (request.args.get('group_name') or request.args.get('group') or '').strip()
+        country = (request.args.get('country') or '').strip().upper()
+        created_from = _parse_admin_datetime_arg('created_from')
+        created_to = _parse_admin_datetime_arg('created_to')
+
+        conditions = [
+            "r.module_type = 'SHOP_DATA_CRAWL'",
+            "t.module_type = 'SHOP_DATA_CRAWL'",
+            "TRIM(COALESCE(r.result_file_url, '')) <> ''",
+        ]
+        params = []
+        if shop_name:
+            conditions.append('r.source_filename LIKE %s')
+            params.append('%' + shop_name + '%')
+        if group_name:
+            conditions.append(
+                'EXISTS (SELECT 1 FROM biz_shop_manage sm '
+                'LEFT JOIN biz_shop_manage_group g ON g.id = sm.group_id '
+                'WHERE TRIM(COALESCE(sm.shop_name, \'\')) = '
+                'TRIM(COALESCE(r.source_filename, \'\')) '
+                "AND COALESCE(NULLIF(g.group_name, ''), NULLIF(sm.group_name, '')) LIKE %s)"
+            )
+            params.append('%' + group_name + '%')
+        if country:
+            if country not in ('DE', 'UK', 'FR', 'IT', 'ES'):
+                raise ValueError('不支持的国家代码: ' + country)
+            conditions.append(
+                'JSON_CONTAINS('
+                'COALESCE(df.country_codes_json, '
+                'JSON_EXTRACT(t.request_json, \'$.countryCodes\'), '
+                'JSON_EXTRACT(t.request_json, \'$.country_codes\'), \'[]\'), %s)'
+            )
+            params.append('"' + country + '"')
+        if created_from:
+            conditions.append('t.created_at >= %s')
+            params.append(created_from)
+        if created_to:
+            conditions.append('t.created_at <= %s')
+            params.append(created_to)
+        where_sql = ' AND '.join(conditions)
+        offset = (page - 1) * page_size
+
+        conn = get_db()
+        try:
+            with conn.cursor() as cur:
+                shop_key_sql = "TRIM(COALESCE(r.source_filename, ''))"
+                grouped_from_sql = (
+                    ' FROM biz_file_result r '
+                    'JOIN biz_file_task t ON t.id = r.task_id '
+                    'LEFT JOIN biz_shop_data_crawl_daily_file df ON df.latest_result_id = r.id '
+                    'LEFT JOIN users u ON u.id = r.user_id '
+                    'WHERE ' + where_sql
+                )
+                cur.execute(
+                    'SELECT COUNT(*) AS total FROM ('
+                    'SELECT ' + shop_key_sql + ' AS shop_key' + grouped_from_sql +
+                    ' GROUP BY ' + shop_key_sql +
+                    ') shop_groups',
+                    tuple(params),
+                )
+                total = int((cur.fetchone() or {}).get('total') or 0)
+
+                cur.execute(
+                    'SELECT ' + shop_key_sql + ' AS shop_name, MAX('
+                    + _SHOP_DATA_CRAWL_LATEST_TIME_SQL + ') AS latest_created_at'
+                    + grouped_from_sql +
+                    ' GROUP BY ' + shop_key_sql +
+                    ' ORDER BY latest_created_at DESC, shop_name ASC LIMIT %s OFFSET %s',
+                    tuple(params + [page_size, offset]),
+                )
+                group_rows = cur.fetchall()
+                group_names = _shop_data_crawl_group_names(cur, group_rows)
+
+                result_rows_by_shop = {}
+                selected_shop_names = [row.get('shop_name') for row in group_rows]
+                if selected_shop_names:
+                    placeholders = ','.join(['%s'] * len(selected_shop_names))
+                    cur.execute(
+                        'SELECT ranked.* FROM (SELECT ' + _SHOP_DATA_CRAWL_ADMIN_COLUMNS +
+                        ', ROW_NUMBER() OVER (PARTITION BY ' + shop_key_sql +
+                        ' ORDER BY ' + _SHOP_DATA_CRAWL_LATEST_TIME_SQL
+                        + ' DESC, r.id DESC) AS shop_row_number '
+                        ' FROM biz_file_result r '
+                        'JOIN biz_file_task t ON t.id = r.task_id '
+                        'LEFT JOIN biz_shop_data_crawl_daily_file df ON df.latest_result_id = r.id '
+                        'LEFT JOIN users u ON u.id = r.user_id '
+                        'WHERE ' + where_sql +
+                        f' AND {shop_key_sql} IN ({placeholders})' +
+                        ') ranked WHERE ranked.shop_row_number <= 1 '
+                        'ORDER BY ranked.latest_file_updated_at DESC, ranked.result_id DESC',
+                        tuple(params + selected_shop_names),
+                    )
+                    for row in cur.fetchall():
+                        shop_key = _shop_data_crawl_shop_key(row.get('shop_name'))
+                        result_rows_by_shop.setdefault(shop_key, []).append(row)
+        finally:
+            conn.close()
+
+        # 逐店读取结果文件并解析（每店最多一个结果文件，共 page_size 个）
+        shop_items = []
+        for rows in result_rows_by_shop.values():
+            for row in rows:
+                result_id = int(row.get('result_id') or 0)
+                if result_id <= 0:
+                    continue
+                try:
+                    raw = _shop_data_crawl_fetch_result_bytes(row)
+                    try:
+                        parsed = _shop_data_crawl_parse_workbook(
+                            load_workbook(io.BytesIO(raw), read_only=True, data_only=True))
+                    except (InvalidFileException, KeyError, ValueError) as exc:
+                        current_app.logger.warning(
+                            '[shop-data-crawl] 解析结果文件失败 result_id=%s: %s', result_id, exc)
+                        continue
+                    shop_items.append({
+                        'shop_name': row.get('shop_name') or '未命名',
+                        'group_name': _shop_data_crawl_group_name(group_names, row.get('shop_name')),
+                        'country_codes': _shop_data_crawl_country_codes_from_json(row.get('country_codes_json'))
+                                       or _shop_data_crawl_country_codes(row.get('request_json')),
+                        'rows': parsed,
+                    })
+                except (requests.RequestException, ValueError) as exc:
+                    current_app.logger.warning(
+                        '[shop-data-crawl] 拉取结果文件失败 result_id=%s: %s', result_id, exc)
+
+        # 按 ASIN 聚合其出现的店铺/分组/国家与行细节
+        asin_occurrences = {}
+        for shop_item in shop_items:
+            shop_name = shop_item['shop_name'] or '未命名'
+            for row in shop_item['rows']:
+                asin = row['asin'].strip().upper()
+                if not asin:
+                    continue
+                asin_occurrences.setdefault(asin, []).append({
+                    'asin': asin,
+                    'date': row['date'],
+                    'price': row['price'],
+                    'brand': row['brand'],
+                    'shop_name': shop_name,
+                    'group_name': shop_item['group_name'],
+                    'country_codes': shop_item['country_codes'],
+                })
+
+        occurrences_list = []
+        for asin, occurrences in asin_occurrences.items():
+            shop_count = len({item['shop_name'] for item in occurrences})
+            if shop_count < 2:
+                continue
+            occurrences_list.append({
+                'asin': asin,
+                'shop_count': shop_count,
+                'occurrences': occurrences,
+            })
+        occurrences_list.sort(key=lambda item: (-item['shop_count'], item['asin']))
+
+        total_details = len(occurrences_list)
+        paged_details = occurrences_list[offset:offset + page_size]
+
+        return jsonify({
+            'success': True,
+            'items': paged_details,
+            'total': total_details,
+            'page': page,
+            'page_size': page_size,
+            'analyzed_shop_count': len(shop_items),
+            'analyzed_result_count': len(shop_items),
+        })
+    except ValueError as exc:
+        return jsonify({'success': False, 'error': str(exc)}), 400
+    except Exception as exc:
+        return _internal_error(exc)
+
+
 def _open_shop_data_crawl_download(row):
     url = f"{backend_java_base_url}/api/admin/shop-data-crawl/results/{int(row['id'])}/download"
     headers, params = _backend_java_internal_request()